Control of a Technological Cycle of Production Process Based on a Neuro-Controller Model

Abstract

In this paper a method for constructing a model of a neuro-controller for implementation of control in the presence of external disturbances for the optimal trajectory finding on the phase plane of system states for technological cycle of a production process is proposed. A type of a neuro-controller based on recurrent neural network architecture with long short-term memory blocks as a knowledge base on the external environment, previous states of the controller and control actions is being used.